作者: Jose M. Perea-Ortega , M. Teresa Martin-Valdivia , Arturo Montejo-Raez , L. Alfonso Urena-Lopez
DOI: 10.1109/SNLP.2009.5340915
关键词:
摘要: This paper describes a basic architecture for retrieving images previously extracted from video files. Our approach is made up of two main subsystems: the speech-based retrieval module and image-based module. The aim experiments presented in this work to establish baseline resolve automatic image task, making use speech content transcripts key frames conclusion indicates that fusion strategies by merging text visual data queries works better than those approaches only textual part or separately. Nevertheless, results obtained confirm content-based IR system it more desirable give weight documents retrieved subsystem subsystem.